© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 1718
    Prev
    Next
    INDEX
    Explanations

    Academy Awards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Night
    0.49
     NIGHT
    0.47
    Night
    0.44
     Dap
    0.42
     nanoc
    0.42
     кристал
    0.42
     night
    0.41
     К
    0.41
    臃
    0.41
     Reich
    0.40
    POSITIVE LOGITS
     mmol
    0.40
    Vad
    0.40
    نیٹ
    0.39
     Merton
    0.38
     Vad
    0.38
     얻
    0.38
     vad
    0.38
    immer
    0.37
    覦
    0.37
    deviceID
    0.37
    Activations Density 0.014%

    No Known Activations